INDEX

Explanations

technical terms and phrases related to engineering and medical research

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

alian

-0.15

izik

-0.15

haar

-0.14

tsky

-0.14

Î¼ÏīÎ½

-0.14

_detalle

-0.13

ÑĸÑĤÑĮ

-0.13

æ¶

-0.13

intl

-0.13

etta

-0.13

POSITIVE LOGITS

Î¯Ïĥ

0.15

 Humans

0.15

Vul

0.15

âĪ¨

0.15

 Kaplan

0.14

 Benchmark

0.14

 PubMed

0.14

0.13

recision

0.13

Activations Density 0.024%

technical terms and phrases related to engineering and medical research

No Comments

No Known Activations